paper-with-me

홈 › Papers

Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

2021-09-05 · EMNLP 2021 11 · Kailong Hao, Botao Yu, Wei Hu

Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB). Due to the incompleteness of current KBs, sentences implying certain relations may be annotated as N/A instances, which causes the so-called false negative (FN) problem. Current RE methods usually overlook this problem, inducing improper biases in both training and testing procedures. To address this issue, we propose a two-stage approach. First, it finds out possible FN samples by heuristically leveraging the memory mechanism of deep neural networks. Then, it aligns those unlabeled data with the training data into a unified feature space by adversarial training to assign pseudo labels and further utilize the information contained in them. Experiments on two wildly-used benchmark datasets demonstrate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2109.02099

Code (1)

nju-websoft/fan 공식 구현 pytorch

Tasks

RelationRelation Extraction

Similar Papers 제목 키워드 기반

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

2023-05-22 · Lu Xu, Lidong Bing, Wei Lu

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a con…

named-entity-recognitionNamed Entity RecognitionNER

Revisiting the Negative Data of Distantly Supervised Relation Extraction

2021-05-21 · ACL 2021 5 · Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang 외

Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reduci…

RelationRelation ExtractionSentence

Combating False Negatives in Adversarial Imitation Learning

2020-02-02 · Konrad Zolna, Chitwan Saharia, Leonard Boussioux, David Yu-Tung Hui 외

In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the…

Imitation Learning

TuckerDNCaching: high-quality negative sampling with tucker decomposition

2023-06-20 · Journal of Intelligent Information Systems 2023 6 · Tiroshan Madushanka, Ryutaro Ichise

Knowledge Graph Embedding (KGE) translates entities and relations of knowledge graphs (KGs) into a low-dimensional vector space, enabling an efficient way of predicting missing facts. Generally, KGE models are trained wi…

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink Prediction

MAFA: Managing False Negatives for Vision-Language Pre-training

2023-12-11 · CVPR 2024 1 · Jaeseok Byun, Dohoon Kim, Taesup Moon

We consider a critical issue of false negatives in Vision-Language Pre-training (VLP), a challenge that arises from the inherent many-to-many correspondence of image-text pairs in large-scale web-crawled datasets. The pr…